arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.00627cs.CLcs.SD
收藏

用于端到端上下文语音识别的树约束指针生成器

Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition

Cambridge University(剑桥大学)

Guangzhi Sun, Chao Zhang, Philip C. Woodland

摘要:

背景知识对于真实世界的自动语音识别(ASR)应用是重要的。在本文中,提出了一种新的树约束指针生成器(TCPGen)组件,将这样的知识作为一个列表的偏置单词到基于注意力的编码器-解码器和换能器端到端ASR模型中的神经符号的方式。TCPGen将偏置词构造成有效的前缀树作为其符号输入,并在树和最终ASR输出分布之间创建神经捷径,以便于在解码期间识别偏置词。在Librispeech语料库上对系统进行了训练和评估,其中在话语,章节或书籍的尺度上提取了偏见词,以模拟不同的应用场景。实验结果表明,TCPGen一贯改善字出错率(WER)相比,基线,特别是,取得了显着的WER减少偏见的话。TCPGen非常高效:它可以处理5,000个偏置词和干扰项,并且只会增加少量的内存使用和计算开销。

英文摘要:

Contextual knowledge is important for real-world automatic speech recognition (ASR) applications. In this paper, a novel tree-constrained pointer generator (TCPGen) component is proposed that incorporates such knowledge as a list of biasing words into both attention-based encoder-decoder and transducer end-to-end ASR models in a neural-symbolic way. TCPGen structures the biasing words into an efficient prefix tree to serve as its symbolic input and creates a neural shortcut between the tree and the final ASR output distribution to facilitate recognising biasing words during decoding. Systems were trained and evaluated on the Librispeech corpus where biasing words were extracted at the scales of an utterance, a chapter, or a book to simulate different application scenarios. Experimental results showed that TCPGen consistently improved word error rates (WERs) compared to the baselines, and in particular, achieved significant WER reductions on the biasing words. TCPGen is highly efficient: it can handle 5,000 biasing words and distractors and only add a small overhead to memory use and computation cost.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑